© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 203973
    Prev
    Next
    INDEX
    Explanations

    language identification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     थे
    0.47
     முன்னோ
    0.46
    *\
    0.45
     soda
    0.43
    DEBUG
    0.43
     visa
    0.42
    除く
    0.42
     беспо
    0.41
    ᅵ
    0.41
    浠
    0.41
    POSITIVE LOGITS
     hvordan
    0.51
     erbjuder
    0.50
     hver
    0.48
     richtigen
    0.48
     Zahlen
    0.47
     navn
    0.46
     اگر
    0.46
    Bună
    0.45
     rikt
    0.45
    vgili
    0.45
    Activations Density 0.002%

    No Known Activations